1. Introduction
Basic Mathematics behind traditional data algorithms, Only topics would be explored for theoretical understanding and no code would be written for the same.
Naive Bayes Classifier
Term Frequency - Inverse Term Frequency
Cosine Similarity
Linear Regression
2. Applications and breakdown,
Tabular Data
Images
Audio
Video
This breakdown along with the detailed analysis on each component would help you figure out how to work on Machine Learning Models.
Most of the research papers whether in computer vision, speech and text need a very good understanding of four things. All of these require thorough understanding along with the code. The idea is to first process them in 3 line definition format and then experiment with the TensorFlow.
Components
Recurrent Neural Networks
Convolutional Neural Networks
Long Short Term Memory Cells
Gated Recurrent Units
Topology Used
Encoder/Decoder
Bidirectional
Grid LSTM
Tree LSTM
Additional factors
Attention
Normalization
Regularization
Share/Unshare Something
Activation Function
TanH
Rectified Linear Unit
Parametric Rectified Linear Unit
Exponential Linear Unit
Sigmoid
Softplus